{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6TXN434E2AHLJYRJQAVXF5MUUQ","short_pith_number":"pith:6TXN434E","schema_version":"1.0","canonical_sha256":"f4eede6f84d00eb4e229802b72f594a41adc6d28b472db93d7a45fed3970f92d","source":{"kind":"arxiv","id":"2607.05614","version":1},"attestation_state":"computed","paper":{"title":"BaFCo: A Document Understanding Benchmark for Complex Bangla Form Comprehension","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Abu Tyeb Azad, AKM Mahbubur Rahman, Aman Chadha, Amin Ahsan Ali, Armun Alam, Ezharuddin Jubaer, Fahim Ahmed, Ishita Sur Apan, Md Mofijul Islam, Pranjal Kumar Nandi, Sumaiya Karim Katha","submitted_at":"2026-07-06T20:17:38Z","abstract_excerpt":"Document comprehension is a challenging yet impactful task for Multimodal Large Language Models, especially as these systems see growing adoption in real-world, human-centric applications. However, this adoption is limited for low-resource languages such as Bangla due to the scarcity of high-quality annotated data. To address this gap, we introduce BaFCo, a benchmark dataset for Bangla form comprehension with a focus on Document Layout Analysis (DLA) and Key Information Extraction (KIE). BaFCo curates 200 multi-page complex Bangladeshi government forms, sourced from across diverse sectors incl"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.05614","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-06T20:17:38Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"2520cf7c73cebfcfdadc25a314ecaabaae6961d2ffe10a67dcf5a73d5ac77464","abstract_canon_sha256":"ce352ada6c769469d291cb2a9ce36a7f7d19fc5ad9ad55c753fdfa5cd0db4524"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-08T01:18:39.224812Z","signature_b64":"mtjysdKJRzMuPu4jqhaaMB3c2hPQRBpwbZkgMtVTPgdjla/aIhzwpl+JG9xB4ZsQ4vDEv8I4KMrG2o6670efDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4eede6f84d00eb4e229802b72f594a41adc6d28b472db93d7a45fed3970f92d","last_reissued_at":"2026-07-08T01:18:39.224155Z","signature_status":"signed_v1","first_computed_at":"2026-07-08T01:18:39.224155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BaFCo: A Document Understanding Benchmark for Complex Bangla Form Comprehension","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Abu Tyeb Azad, AKM Mahbubur Rahman, Aman Chadha, Amin Ahsan Ali, Armun Alam, Ezharuddin Jubaer, Fahim Ahmed, Ishita Sur Apan, Md Mofijul Islam, Pranjal Kumar Nandi, Sumaiya Karim Katha","submitted_at":"2026-07-06T20:17:38Z","abstract_excerpt":"Document comprehension is a challenging yet impactful task for Multimodal Large Language Models, especially as these systems see growing adoption in real-world, human-centric applications. However, this adoption is limited for low-resource languages such as Bangla due to the scarcity of high-quality annotated data. To address this gap, we introduce BaFCo, a benchmark dataset for Bangla form comprehension with a focus on Document Layout Analysis (DLA) and Key Information Extraction (KIE). BaFCo curates 200 multi-page complex Bangladeshi government forms, sourced from across diverse sectors incl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.05614","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.05614/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.05614","created_at":"2026-07-08T01:18:39.224247+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.05614v1","created_at":"2026-07-08T01:18:39.224247+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.05614","created_at":"2026-07-08T01:18:39.224247+00:00"},{"alias_kind":"pith_short_12","alias_value":"6TXN434E2AHL","created_at":"2026-07-08T01:18:39.224247+00:00"},{"alias_kind":"pith_short_16","alias_value":"6TXN434E2AHLJYRJ","created_at":"2026-07-08T01:18:39.224247+00:00"},{"alias_kind":"pith_short_8","alias_value":"6TXN434E","created_at":"2026-07-08T01:18:39.224247+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6TXN434E2AHLJYRJQAVXF5MUUQ","json":"https://pith.science/pith/6TXN434E2AHLJYRJQAVXF5MUUQ.json","graph_json":"https://pith.science/api/pith-number/6TXN434E2AHLJYRJQAVXF5MUUQ/graph.json","events_json":"https://pith.science/api/pith-number/6TXN434E2AHLJYRJQAVXF5MUUQ/events.json","paper":"https://pith.science/paper/6TXN434E"},"agent_actions":{"view_html":"https://pith.science/pith/6TXN434E2AHLJYRJQAVXF5MUUQ","download_json":"https://pith.science/pith/6TXN434E2AHLJYRJQAVXF5MUUQ.json","view_paper":"https://pith.science/paper/6TXN434E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.05614&json=true","fetch_graph":"https://pith.science/api/pith-number/6TXN434E2AHLJYRJQAVXF5MUUQ/graph.json","fetch_events":"https://pith.science/api/pith-number/6TXN434E2AHLJYRJQAVXF5MUUQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6TXN434E2AHLJYRJQAVXF5MUUQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6TXN434E2AHLJYRJQAVXF5MUUQ/action/storage_attestation","attest_author":"https://pith.science/pith/6TXN434E2AHLJYRJQAVXF5MUUQ/action/author_attestation","sign_citation":"https://pith.science/pith/6TXN434E2AHLJYRJQAVXF5MUUQ/action/citation_signature","submit_replication":"https://pith.science/pith/6TXN434E2AHLJYRJQAVXF5MUUQ/action/replication_record"}},"created_at":"2026-07-08T01:18:39.224247+00:00","updated_at":"2026-07-08T01:18:39.224247+00:00"}